Using machine learning to impact on long-term clinical care: principles, challenges, and practicalities

The use of machine learning in paediatric nutrition

PURPOSE OF REVIEW

In recent years, there has been a burgeoning interest in using machine learning methods. This has been accompanied by an expansion in the availability and ease of use of machine learning tools and an increase in the number of large, complex datasets which are suited to machine learning approaches. This review summarizes recent work in the field and sets expectations for its impact in the future.

RECENT FINDINGS

Much work has focused on establishing good practices and ethical frameworks to guide the use of machine learning in research. Machine learning has an established role in identifying features in 'omics' research and is emerging as a tool to generate predictive models to identify people at risk of disease and patients at risk of complications. They have been used to identify risks for malnutrition and obesity. Machine learning techniques have also been used to develop smartphone apps to track behaviour and provide healthcare advice.

SUMMARY

Machine learning techniques are reaching maturity and their impact on observational data analysis and behaviour change will come to fruition in the next 5 years. A set of standards and best practices are emerging and should be implemented by researchers and publishers.

Use of machine learning models for the prognostication of liver transplantation: A systematic review

BACKGROUND

Liver transplantation (LT) is a life-saving intervention for patients with end-stage liver disease. However, the equitable allocation of scarce donor organs remains a formidable challenge. Prognostic tools are pivotal in identifying the most suitable transplant candidates. Traditionally, scoring systems like the model for end-stage liver disease have been instrumental in this process. Nevertheless, the landscape of prognostication is undergoing a transformation with the integration of machine learning (ML) and artificial intelligence models.

AIM

To assess the utility of ML models in prognostication for LT, comparing their per formance and reliability to established traditional scoring systems.

METHODS

Following the Preferred Reporting Items for Systematic Reviews and Meta-Analysis guidelines, we conducted a thorough and standardized literature search using the PubMed/MEDLINE database. Our search imposed no restrictions on publication year, age, or gender. Exclusion criteria encompassed non-English stu dies, review articles, case reports, conference papers, studies with missing data, or those exhibiting evident methodological flaws.

RESULTS

Our search yielded a total of 64 articles, with 23 meeting the inclusion criteria. Among the selected studies, 60.8% originated from the United States and China combined. Only one pediatric study met the criteria. Notably, 91% of the studies were published within the past five years. ML models consistently demonstrated satisfactory to excellent area under the receiver operating characteristic curve values (ranging from 0.6 to 1) across all studies, surpassing the performance of traditional scoring systems. Random forest exhibited superior predictive capa bilities for 90-d mortality following LT, sepsis, and acute kidney injury (AKI). In contrast, gradient boosting excelled in predicting the risk of graft-versus-host disease, pneumonia, and AKI.

CONCLUSION

This study underscores the potential of ML models in guiding decisions related to allograft allocation and LT, marking a significant evolution in the field of prognostication.

Exploring the opportunities and challenges of implementing artificial intelligence in healthcare: A systematic literature review

Recent progress in the realm of artificial intelligence has shown effectiveness in various industries, particularly within the healthcare sector. However, there are limited insights on existing studies regarding ethical, social, privacy, and technological aspects of AI in the health sector, which is the gap our study aims to fill. This study aimed to synthesize empirical studies on the challenges and opportunities of using AI by conducting a systematic review. We reviewed 33 articles published between 2015 and 2022 in the PubMed, IEEE Xplore, and Science Direct databases. The results show that artificial intelligence has the promise of improving health care and faces obstacles when implemented. Most of the reviewed studies indicated that the use of AI provides several opportunities, including teamwork and decision-making, technological advancement, diagnosis and patient monitoring, drug development, and virtual health assistance. However, the findings show that the use of AI in the health sector hinders multifaceted challenges, including ethical and privacy-related issues, lack of awareness, unreliability of technology, and professional liability. The findings highlight that artificial intelligence has the potential to transform healthcare and that addressing these challenges is crucial to fully utilize its potential.

Recent advancement in integrating artificial intelligence and information technology with real-world data for clinical decision-making in China: A scoping review

OBJECTIVE

Striking innovations and advancements have been achieved with the use of artificial intelligence and healthcare information technology being integrated into clinical real-world data. The current scoping review aimed to provide an overview of the current status of artificial intelligence-/information technology-based clinical decision support tools in China.

METHODS

PubMed/MEDLINE, Embase, China National Knowledge Internet, and Wanfang data were searched for both English and Chinese literature. The gray literature search was conducted for commercially available tools. Original studies that focused on clinical decision support tools driven by artificial intelligence or information technology in China and were published between 2010 and February 2022 were included. Information extracted from each article was further synthesized by themes based on three types of clinical decision-making.

RESULTS

A total of 37 peer-reviewed publications and 13 commercially available tools were included in the final analysis. Among them, 32.0% were developed for disease diagnosis, 54.0% for risk prediction and classification, and 14.0% for disease management. Chronic diseases were the most popular therapeutic areas of exploration, with particular emphasis on cardiovascular and cerebrovascular diseases. Single-center electronic medical records were the mainstream data sources leveraged to inform clinical decision-making, with internal validation being predominately used for model evaluation.

CONCLUSIONS

To effectively promote the extensive use of real-world data and drive a paradigm shift in clinical decision-making in China, multidisciplinary collaboration of key stakeholders is urgently needed.

Finding the best trade-off between performance and interpretability in predicting hospital length of stay using structured and unstructured data

OBJECTIVE

This study aims to develop high-performing Machine Learning and Deep Learning models in predicting hospital length of stay (LOS) while enhancing interpretability. We compare performance and interpretability of models trained only on structured tabular data with models trained only on unstructured clinical text data, and on mixed data.

METHODS

The structured data was used to train fourteen classical Machine Learning models including advanced ensemble trees, neural networks and k-nearest neighbors. The unstructured data was used to fine-tune a pre-trained Bio Clinical BERT Transformer Deep Learning model. The structured and unstructured data were then merged into a tabular dataset after vectorization of the clinical text and a dimensional reduction through Latent Dirichlet Allocation. The study used the free and publicly available Medical Information Mart for Intensive Care (MIMIC) III database, on the open AutoML Library AutoGluon. Performance is evaluated with respect to two types of random classifiers, used as baselines.

RESULTS

The best model from structured data demonstrates high performance (ROC AUC = 0.944, PRC AUC = 0.655) with limited interpretability, where the most important predictors of prolonged LOS are the level of blood urea nitrogen and of platelets. The Transformer model displays a good but lower performance (ROC AUC = 0.842, PRC AUC = 0.375) with a richer array of interpretability by providing more specific in-hospital factors including procedures, conditions, and medical history. The best model trained on mixed data satisfies both a high level of performance (ROC AUC = 0.963, PRC AUC = 0.746) and a much larger scope in interpretability including pathologies of the intestine, the colon, and the blood; infectious diseases, respiratory problems, procedures involving sedation and intubation, and vascular surgery.

CONCLUSIONS

Our results outperform most of the state-of-the-art models in LOS prediction both in terms of performance and of interpretability. Data fusion between structured and unstructured text data may significantly improve performance and interpretability.

Artificial Intelligence Models in Health Information Exchange: A Systematic Review of Clinical Implications

Electronic health record (EHR) systems collate patient data, and the integration and standardization of documents through Health Information Exchange (HIE) play a pivotal role in refining patient management. Although the clinical implications of AI in EHR systems have been extensively analyzed, its application in HIE as a crucial source of patient data is less explored. Addressing this gap, our systematic review delves into utilizing AI models in HIE, gauging their predictive prowess and potential limitations. Employing databases such as Scopus, CINAHL, Google Scholar, PubMed/Medline, and Web of Science and adhering to the PRISMA guidelines, we unearthed 1021 publications. Of these, 11 were shortlisted for the final analysis. A noticeable preference for machine learning models in prognosticating clinical results, notably in oncology and cardiac failures, was evident. The metrics displayed AUC values ranging between 61% and 99.91%. Sensitivity metrics spanned from 12% to 96.50%, specificity from 76.30% to 98.80%, positive predictive values varied from 83.70% to 94.10%, and negative predictive values between 94.10% and 99.10%. Despite variations in specific metrics, AI models drawing on HIE data unfailingly showcased commendable predictive proficiency in clinical verdicts, emphasizing the transformative potential of melding AI with HIE. However, variations in sensitivity highlight underlying challenges. As healthcare's path becomes more enmeshed with AI, a well-rounded, enlightened approach is pivotal to guarantee the delivery of trustworthy and effective AI-augmented healthcare solutions.

Hyperparameter optimization for cardiovascular disease data-driven prognostic system

Prediction and diagnosis of cardiovascular diseases (CVDs) based, among other things, on medical examinations and patient symptoms are the biggest challenges in medicine. About 17.9 million people die from CVDs annually, accounting for 31% of all deaths worldwide. With a timely prognosis and thorough consideration of the patient's medical history and lifestyle, it is possible to predict CVDs and take preventive measures to eliminate or control this life-threatening disease. In this study, we used various patient datasets from a major hospital in the United States as prognostic factors for CVD. The data was obtained by monitoring a total of 918 patients whose criteria for adults were 28-77 years old. In this study, we present a data mining modeling approach to analyze the performance, classification accuracy and number of clusters on Cardiovascular Disease Prognostic datasets in unsupervised machine learning (ML) using the Orange data mining software. Various techniques are then used to classify the model parameters, such as k-nearest neighbors, support vector machine, random forest, artificial neural network (ANN), naïve bayes, logistic regression, stochastic gradient descent (SGD), and AdaBoost. To determine the number of clusters, various unsupervised ML clustering methods were used, such as k-means, hierarchical, and density-based spatial clustering of applications with noise clustering. The results showed that the best model performance analysis and classification accuracy were SGD and ANN, both of which had a high score of 0.900 on Cardiovascular Disease Prognostic datasets. Based on the results of most clustering methods, such as k-means and hierarchical clustering, Cardiovascular Disease Prognostic datasets can be divided into two clusters. The prognostic accuracy of CVD depends on the accuracy of the proposed model in determining the diagnostic model. The more accurate the model, the better it can predict which patients are at risk for CVD.

A Diagnostic Gene-Expression Signature in Fibroblasts of Amyotrophic Lateral Sclerosis

Amyotrophic lateral sclerosis (ALS) is a fatal, progressive neurodegenerative disease with limited treatment options. Diagnosis can be difficult due to the heterogeneity and non-specific nature of the initial symptoms, resulting in delays that compromise prompt access to effective therapeutic strategies. Transcriptome profiling of patient-derived peripheral cells represents a valuable benchmark in overcoming such challenges, providing the opportunity to identify molecular diagnostic signatures. In this study, we characterized transcriptome changes in skin fibroblasts of sporadic ALS patients (sALS) and controls and evaluated their utility as a molecular classifier for ALS diagnosis. Our analysis identified 277 differentially expressed transcripts predominantly involved in transcriptional regulation, synaptic transmission, and the inflammatory response. A support vector machine classifier based on this 277-gene signature was developed to discriminate patients with sALS from controls, showing significant predictive power in both the discovery dataset and in six independent publicly available gene expression datasets obtained from different sALS tissue/cell samples. Taken together, our findings support the utility of transcriptional signatures in peripheral cells as valuable biomarkers for the diagnosis of ALS.

Joint use of population pharmacokinetics and machine learning for optimizing antiepileptic treatment in pediatric population

Purpose

Unpredictable drug efficacy and safety of combined antiepileptic therapy is a major challenge during pharmacotherapy decisions in everyday clinical practice. The aim of this study was to describe the pharmacokinetics of valproic acid (VA), lamotrigine (LTG), and levetiracetam (LEV) in a pediatric population using nonlinear mixed-effect modeling, while machine learning (ML) algorithms were applied to identify any relationships among the plasma levels of the three medications and patients' characteristics, as well as to develop a predictive model for epileptic seizures.

Methods

The study included 71 pediatric patients of both genders, aged 2-18 years, on combined antiepileptic therapy. Population pharmacokinetic (PopPK) models were developed separately for VA, LTG, and LEV. Based on the estimated pharmacokinetic parameters and the patients' characteristics, three ML approaches were applied (principal component analysis, factor analysis of mixed data, and random forest). PopPK models and ML models were developed, allowing for greater insight into the treatment of children on antiepileptic treatment.

Results

Results from the PopPK model showed that the kinetics of LEV, LTG, and VA were best described by a one compartment model with first-order absorption and elimination kinetics. Reliance on random forest model is a compelling vision that shows high prediction ability for all cases. The main factor that can affect antiepileptic activity is antiepileptic drug levels, followed by body weight, while gender is irrelevant. According to our study, children's age is positively associated with LTG levels, negatively with LEV and without the influence of VA.

Conclusion

The application of PopPK and ML models may be useful to improve epilepsy management in vulnerable pediatric population during the period of growth and development.